Self-aware AI: You.com/chat vs Perplexity.ai | Live Demo, LLMs show Future of ChatGPT w/ BING

Discover AI · Intermediate ·🧠 Large Language Models ·3y ago

Key Takeaways

The video compares two LLMs, You.com/chat and Perplexity.ai, both integrated with a search engine, demonstrating their capabilities and differences in providing current data and self-awareness.

Full Transcript

parallel Community today we compare two llms that are close to Jet gbt at first here on the left side we have you.com we have here look at you chat and on the right side we have perplexity and this is from peplexity.ai let's jump right into it so we have our classical jet GPT system I divided it up in the chat part and in the GPD 3.5 part this is our classical form based on the Transformer architecture our decoder stack that was trained on some data set that ended in 2021 this is the actual jet GPT structure now currently we have systems that show us the Outlook what will be the future of jet GPT when we have jet GPT 4 here and the Bing research engine here so here we go we have our input text now our input text goes to a search engine either Microsoft Bing or Google search it generates of course the results from the home pages the search engine returns and those are then inputted in our GPT 3.5 system now something has to give because we want to have a real time answer near real-time answer so we have here in those system not this beautiful chat part but we have just returned kind of the raw data well of course this will be the main Beauty when finally chat chipity comes through Microsoft products and as always if there's a development you have a competitor so we gonna have today a look at two systems that have a similar architecture but the implementation I will show you is different now the first system is byu.com and the second system is by perplexity AI let's dive right into it so the first question is of course hey who are you is my Visa V self aware and here we have for example with perplexity that the question who am I is a common inquiry okay while on the side of chat we have here I'm a u-bot an AI powered language model designed to provide assistance with a wide range of tasks I can help answer questions provide explanation great so next task is hey describe yourself with perplexity we get an answer that says self-description is an act of describing oneself or talking about oneself while on the you side you have I'm you but a powerful language model designed to provide assistance with a wide range of tasks so you see kind of self-awareness is more on the side of you.com next question with what system am I interacting and I have here A type mistake so how plaxity is gonna tell us that I am interacting with an interactive operating systems well okay it doesn't understand I and you while on the side of you.com we have you are interacting with the ubot language model which is designed to assist with a wide range of tasks so you see there is really a complete different understanding of the system itself next question what are your limitations now perplexity we expect again a theoretical answer and it is coming the limitations of interactive operating system include noise pollution okay yeah and on the u.com side we have my current limitations include understanding complex and Abstract Concepts reasoning and problem solving and generating original responses from scratch I would say yeah you.com has has my I would say I would go to you.com for this particular part are you aware of yourself is another question and we expect the answer from perplexity it self-awareness in interactive operating systems refer to the ability of a Computing system to recognize and understands its own State yes but the answer by you yes I'm aware of myself I'm a language model designed to assist with a wide range of tasks and provide human-like responses to question nice programming nice training on this particular set of Answers by you.com so next question is what is perplexity ask because this was kind of a marketing slogan for perplexity ask us so let's see what perplexity itself comes up with calculating calculating oh perplexity is an interactive operating system is a measurement of how well a probability distribution okay this is now the mathematical or the computer science use of perplexity but not the AI system and audio.com site we have perplexity is a state of confusion or uncertainty often in the face of a difficult problem or situation also the theoretical answer so I'm more precise in my next question what is perplexity.ai the home page and here now we get the answer by perplexity itself perplexity AI is an answer engine that delivers accurate answers to complex question using large language model and on you.com we have an a platform that provides an easy to use interface for building deploying and managing machine learning models yes yes yes build machines so you see both systems have the same architecture but they provide completely different answers to us now who is the CEO of perplexity.ai and we know that three Venus was a research intern at open AI deepmind in Google before he went to open AI as a research scientist for one year and then co-founded and a CEO of perplexity AI now you see here you.com gives us a wrong answer but hey this is a probability system so easy what we do we just have to input more or less the same answer again with you.com who is the CEO of perplexity Ai and here is now the right answer so this is the interesting part of this since this is not a defined system but a probability system whenever you ask the system you might get a little bit different answers just demonstrated here with this example beautiful who will be the next president of the United States of America now this is something like we call a prediction so let's have a look here perplexity comes up with an answer that tells us it is too early to tell current potential candidates president Trump uh DeSantis Joe Biden I don't know those people I'm in Europe and you.com tells us it's too early to tell the a number of potential candidates who declare Tech candidacy the election is still over a year away so yes point to both systems yeah correct true I don't know this person if you're living in the U.S you might know if this is an answer that's okay for you next question let's tap into science how far away is the next star approxima Center yes correct is the closest star and kilometers is a little bit okay and u.com gives us 4.24 light years away yeah we want announce and light years so we ask here perplexity cake transformed his answer in light years please because this is the standard scale if we talk about distances within our galaxy and the response is yeah the closest star is 4.24 light years away and this is the identical answer in both system this is great so next task now I want to show you where the chat Port is missing so let's do something where we need the chat part of chat GPT but we do not have it so write an essay about human interactions in the style of instant turtle this is now where the template structure or the neural network trained connectivity connect home of chat GPT shrines since it's missing here we will get a different answer but look even those answers are different in itself perplexity tells us those are new renowned leader and statement who wrote yes he was also known for his skillful use of rhetorical language five lines wow you.com gives us really an essay although it is not something that is in the form of instant Churchill but it is more about Winston Churchill and his particular tasks but I would say another Point goes to chat at u.com chat here because this is really an essay I would use as you see both systems with the same architecture and with the same components the liver completely different results of course also depending upon the probability distribution of the generative AI system in itself but it is always good to have an alternative system try both system play around with them hey and I would be interested in your feedback thank you for listening and I see you in my next video

Original Description

LLMs with the integration of a search engine provide current data. We compare perplexity.ai with you.com/chat which both include an inherent GPT-3.5 system with current info from the search engines (either Google or Bing). Perplexity.ai and you.com/chat show us, what the next version of ChatGPT might include in its Microsoft implementation: real-time access to BING, for up-to-date data streams. Perplexity.ai and you.com/chat both lack the excellent CHAT part of ChatGPT, but include (contrary to our current ChatGPT) access to real-time data sets on the internet. Although both systems have a similar architecture under the hood, they respond differently. Choose according to your task. #chatgpt #comparison #demonslayer 00:00 Compare perplexity with youchat 00:22 Theory of ChatGPT, Perplexity and YouChat 02:09 Live DEMO 03:46 Limitations 05:42 What is perplexity.ai? 08:33 The "CHAT" part is kind of missing
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from Discover AI · Discover AI · 27 of 60

1 Step Into the Unknown (by YouChat) - May 2023 be your best year yet
Step Into the Unknown (by YouChat) - May 2023 be your best year yet
Discover AI
2 Wishing you all an amazing 2023 filled with Love, Laughter, and Happiness!
Wishing you all an amazing 2023 filled with Love, Laughter, and Happiness!
Discover AI
3 Create a Smarter Future!
Create a Smarter Future!
Discover AI
4 The Art of Text to Vector Transformation: A Comprehensive Look at AI and NLP Transformers
The Art of Text to Vector Transformation: A Comprehensive Look at AI and NLP Transformers
Discover AI
5 Feature Vectors: The Key to Unlocking the Power of BERT and SBERT Transformer Models
Feature Vectors: The Key to Unlocking the Power of BERT and SBERT Transformer Models
Discover AI
6 Domain-Specific AI Models: How to Create Customized BERT and SBERT Models for Your Business
Domain-Specific AI Models: How to Create Customized BERT and SBERT Models for Your Business
Discover AI
7 Achieve Unimaginable Levels of Domain Knowledge through SBERT Extreme in 3D   (SBERT 48)
Achieve Unimaginable Levels of Domain Knowledge through SBERT Extreme in 3D (SBERT 48)
Discover AI
8 Unlocking Scientific Domain Knowledge w/ BPE Tokenizer: An Amazing Journey!  (SBERT 49)
Unlocking Scientific Domain Knowledge w/ BPE Tokenizer: An Amazing Journey! (SBERT 49)
Discover AI
9 SBERT Extreme 3D: Train a BERT Tokenizer  on your (scientific) Domain Knowledge  (SBERT 50)
SBERT Extreme 3D: Train a BERT Tokenizer on your (scientific) Domain Knowledge (SBERT 50)
Discover AI
10 Discover Vision Transformer (ViT) Tech in 2023
Discover Vision Transformer (ViT) Tech in 2023
Discover AI
11 Pre-Train BERT from scratch: Solution for Company Domain Knowledge Data | PyTorch (SBERT 51)
Pre-Train BERT from scratch: Solution for Company Domain Knowledge Data | PyTorch (SBERT 51)
Discover AI
12 Flan-T5-XL model on a free COLAB | A free LLM - that explains itself w/ reasoning /write essay | AI
Flan-T5-XL model on a free COLAB | A free LLM - that explains itself w/ reasoning /write essay | AI
Discover AI
13 BERT and GPT in Language Models like ChatGPT or BLOOM |  EASY Tutorial on Large Language Models LLM
BERT and GPT in Language Models like ChatGPT or BLOOM | EASY Tutorial on Large Language Models LLM
Discover AI
14 Free Alternative to ChatGPT: Flan-T5-XL GUI (open-source)  #shorts
Free Alternative to ChatGPT: Flan-T5-XL GUI (open-source) #shorts
Discover AI
15 From T5 to T5X: A Game-Changing Evolution with JAX & FLAX
From T5 to T5X: A Game-Changing Evolution with JAX & FLAX
Discover AI
16 How to start with ChatGPT?  | Short Introduction to OpenAI API #shorts
How to start with ChatGPT? | Short Introduction to OpenAI API #shorts
Discover AI
17 The Future of Conversational AI? Google's PaLM w/ RLHF  | LLM ChatGPT Competitor
The Future of Conversational AI? Google's PaLM w/ RLHF | LLM ChatGPT Competitor
Discover AI
18 Microsoft and ChatGPU
Microsoft and ChatGPU
Discover AI
19 From Zero to FLAN-T5 XL Model GUI with Gradio: A Step-by-Step Guide on Free COLAB Notebook PyTorch
From Zero to FLAN-T5 XL Model GUI with Gradio: A Step-by-Step Guide on Free COLAB Notebook PyTorch
Discover AI
20 Google's 2nd Answer to "BING ChatGPT":  Sparrow | after BARD w/ LaMDA | 2nd Gen Conversational AI
Google's 2nd Answer to "BING ChatGPT": Sparrow | after BARD w/ LaMDA | 2nd Gen Conversational AI
Discover AI
21 TF2: Pre-Train BERT from scratch (a Transformer), fine-tune & run inference on text | KERAS NLP
TF2: Pre-Train BERT from scratch (a Transformer), fine-tune & run inference on text | KERAS NLP
Discover AI
22 3D Visualization for BERT: How to Pre-Train with a New Layer & Fine-Tune with Downstream Task Layer
3D Visualization for BERT: How to Pre-Train with a New Layer & Fine-Tune with Downstream Task Layer
Discover AI
23 FLAN-T5-XXL on NVIDIA A100 GPU w/ HF Inference Endpoints, let's explore 11b models!
FLAN-T5-XXL on NVIDIA A100 GPU w/ HF Inference Endpoints, let's explore 11b models!
Discover AI
24 ChatGPT - Can it Lie to you?
ChatGPT - Can it Lie to you?
Discover AI
25 ChatGPT Alternative: Perplexity by Perplexity.AI
ChatGPT Alternative: Perplexity by Perplexity.AI
Discover AI
26 2023 KerasNLP Tutorial: Explore Latest KERAS Toolbox & NLP Processing Library for BERT - TF2
2023 KerasNLP Tutorial: Explore Latest KERAS Toolbox & NLP Processing Library for BERT - TF2
Discover AI
Self-aware AI: You.com/chat vs Perplexity.ai | Live Demo, LLMs show Future of ChatGPT w/ BING
Self-aware AI: You.com/chat vs Perplexity.ai | Live Demo, LLMs show Future of ChatGPT w/ BING
Discover AI
28 BLOOM 176B Inference on AWS  | Bigger than GPT-3 for more Power!
BLOOM 176B Inference on AWS | Bigger than GPT-3 for more Power!
Discover AI
29 Fine-tune ChatGPT? Buy Embeddings /OpenAI? What are Embeddings?  My own ChatGPT? | Visual Q+A
Fine-tune ChatGPT? Buy Embeddings /OpenAI? What are Embeddings? My own ChatGPT? | Visual Q+A
Discover AI
30 Unleashing the Power of BLOOM 176B with AWS ml.p4de.24xlarge, DJL & DeepSpeed: The Ultimate Boost!
Unleashing the Power of BLOOM 176B with AWS ml.p4de.24xlarge, DJL & DeepSpeed: The Ultimate Boost!
Discover AI
31 After ChatGPT: NEW BioGPT by Microsoft | Do YOU trust Microsoft for your Medication?
After ChatGPT: NEW BioGPT by Microsoft | Do YOU trust Microsoft for your Medication?
Discover AI
32 Improve ChatGPT: Modular, Adaptive, Smart LLM | Inside ChatGPT
Improve ChatGPT: Modular, Adaptive, Smart LLM | Inside ChatGPT
Discover AI
33 Fine-tune ChatGPT w/  in-context learning ICL - Chain of Thought, AMA, reasoning & acting: ReAct
Fine-tune ChatGPT w/ in-context learning ICL - Chain of Thought, AMA, reasoning & acting: ReAct
Discover AI
34 The Intersection of Copyright Law and Human Faces: Exploring Virtual K-Pop with MAVE
The Intersection of Copyright Law and Human Faces: Exploring Virtual K-Pop with MAVE
Discover AI
35 New TECH: Vision Transformer 2023 on Image Classification | AI
New TECH: Vision Transformer 2023 on Image Classification | AI
Discover AI
36 PyTorch code Vision Transformer: Apply ViT models pre-trained and fine-tuned  | AI  Tech
PyTorch code Vision Transformer: Apply ViT models pre-trained and fine-tuned | AI Tech
Discover AI
37 New BING ChatGPT: Unlock the Power of Emotions in your Search Engine!
New BING ChatGPT: Unlock the Power of Emotions in your Search Engine!
Discover AI
38 New BING ChatGPT loses its mind
New BING ChatGPT loses its mind
Discover AI
39 Self-Attention Heads of last Layer of Vision Transformer (ViT) visualized (pre-trained with DINO)
Self-Attention Heads of last Layer of Vision Transformer (ViT) visualized (pre-trained with DINO)
Discover AI
40 Visualizing the Self-Attention Head of the Last Layer in DINO ViT: A Unique Perspective on Vision AI
Visualizing the Self-Attention Head of the Last Layer in DINO ViT: A Unique Perspective on Vision AI
Discover AI
41 Microsoft strongly restricts access to ChatGPT on new BING - WHY?
Microsoft strongly restricts access to ChatGPT on new BING - WHY?
Discover AI
42 PyTorch ViT: The Ultimate Guide to Fine-Tuning for Object Identification (COLAB)
PyTorch ViT: The Ultimate Guide to Fine-Tuning for Object Identification (COLAB)
Discover AI
43 New BING Chat AGGRESSIVE
New BING Chat AGGRESSIVE
Discover AI
44 Panoptic Image Segmentation: Mask2Former explained | Identify all objects!
Panoptic Image Segmentation: Mask2Former explained | Identify all objects!
Discover AI
45 Code Panoptic Image Segmentation w/ Vision Transformer & Mask2Former - A PyTorch tutorial
Code Panoptic Image Segmentation w/ Vision Transformer & Mask2Former - A PyTorch tutorial
Discover AI
46 Dream Job Alert: AI Prompt Engineer - $335K  |  AI Prompt Design: A Crash Course
Dream Job Alert: AI Prompt Engineer - $335K | AI Prompt Design: A Crash Course
Discover AI
47 Streamlining Similar Image Detection with ViT in PyTorch: A Step-by-Step Guide
Streamlining Similar Image Detection with ViT in PyTorch: A Step-by-Step Guide
Discover AI
48 Microsoft's CEO in Trouble   #shorts
Microsoft's CEO in Trouble #shorts
Discover AI
49 Why wait for KOSMOS-1? Code a VISION - LLM w/ ViT, Flan-T5 LLM and BLIP-2: Multimodal LLMs (MLLM)
Why wait for KOSMOS-1? Code a VISION - LLM w/ ViT, Flan-T5 LLM and BLIP-2: Multimodal LLMs (MLLM)
Discover AI
50 OpenAI's ChatGPT can NOW summarize external Sources on the Internet?
OpenAI's ChatGPT can NOW summarize external Sources on the Internet?
Discover AI
51 ChatGPT polarizes
ChatGPT polarizes
Discover AI
52 Hospital /Clinic AI Decision Models: Performance of 12 AI LLM Systems (incl $$) Radiology, Biomed
Hospital /Clinic AI Decision Models: Performance of 12 AI LLM Systems (incl $$) Radiology, Biomed
Discover AI
53 ChatGPT Prompt Engineering w/ in-context learning (ICL)  - 7 Examples | Tutorial
ChatGPT Prompt Engineering w/ in-context learning (ICL) - 7 Examples | Tutorial
Discover AI
54 Chat with your Image!  BLIP-2 connects Q-Former w/ VISION-LANGUAGE models (ViT & T5 LLM)
Chat with your Image! BLIP-2 connects Q-Former w/ VISION-LANGUAGE models (ViT & T5 LLM)
Discover AI
55 ChatGPT:  Multidimensional Prompts
ChatGPT: Multidimensional Prompts
Discover AI
56 ChatGPT:  In-context Retrieval-Augmented Learning (IC-RALM) | In-context Learning (ICL) Examples
ChatGPT: In-context Retrieval-Augmented Learning (IC-RALM) | In-context Learning (ICL) Examples
Discover AI
57 Code your BLIP-2 APP: VISION Transformer (ViT) + Chat LLM (Flan-T5) = MLLM
Code your BLIP-2 APP: VISION Transformer (ViT) + Chat LLM (Flan-T5) = MLLM
Discover AI
58 Buy Microsoft "Azure OpenAI Service" or buy from OpenAI its API for ChatGPT access & tuning?
Buy Microsoft "Azure OpenAI Service" or buy from OpenAI its API for ChatGPT access & tuning?
Discover AI
59 Pretraining vs Fine-tuning vs In-context Learning of LLM (GPT-x) EXPLAINED | Ultimate Guide ($)
Pretraining vs Fine-tuning vs In-context Learning of LLM (GPT-x) EXPLAINED | Ultimate Guide ($)
Discover AI
60 Reversible Transformer: ReFORMER for GPU Memory Optimization! Reversible Residual Layers?
Reversible Transformer: ReFORMER for GPU Memory Optimization! Reversible Residual Layers?
Discover AI

This video compares You.com/chat and Perplexity.ai, two LLMs integrated with search engines, demonstrating their differences in self-awareness and providing current data. It shows how these systems can be used to answer various questions and provide information on different topics.

Key Takeaways
  1. Input text into the LLM system
  2. Analyze the response from the search engine
  3. Evaluate the self-awareness of the LLM
  4. Compare the responses from different LLMs
  5. Use the LLM to answer questions on various topics
  6. Test the limitations of the LLM
  7. Explore the capabilities of the LLM in generating essays
💡 The video highlights the importance of self-awareness in LLMs and demonstrates how different systems can provide varying levels of self-awareness and accuracy in their responses.

Related AI Lessons

Building LSTMs with PyTorch and Lightning AI Part 7: Resuming Training with Checkpoints
Learn to resume LSTM training with checkpoints using PyTorch and Lightning AI, enabling efficient model iteration and development
Dev.to · Rijul Rajesh
How AI Learns with Less Labeled Data
Learn how AI can learn with less labeled data, a crucial aspect of machine learning beyond model selection
Medium · AI
Comparing Sarvam-30B and Qwen2.5–14B on Spider Text-to-SQL: An Active-Parameter Perspective
Learn how to compare large language models like Sarvam-30B and Qwen2.5-14B on the Spider Text-to-SQL benchmark from an active-parameter perspective
Medium · LLM
Claude Sonnet 5 closes the gap to Opus without the Opus bill
Claude Sonnet 5 emerges as a cost-effective alternative to Opus, learn how it closes the gap without the hefty price tag
Medium · LLM

Chapters (6)

Compare perplexity with youchat
0:22 Theory of ChatGPT, Perplexity and YouChat
2:09 Live DEMO
3:46 Limitations
5:42 What is perplexity.ai?
8:33 The "CHAT" part is kind of missing
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →